Search Results for author: Elena Burceanu

Found 10 papers, 6 papers with code

Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Time

no code implementations15 Dec 2022 Elena Burceanu, Marius Leordeanu

Our motivation for a spectral space-time clustering approach, unique in video semantic segmentation literature, is that such clustering is dedicated to preserving object consistency over time, which we evaluate using our novel segmentation consistency measure.

Graph Clustering Object Tracking +4

Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!

no code implementations6 Oct 2022 Stefan Smeu, Elena Burceanu, Andrei Liviu Nicolicioiu, Emanuela Haller

We introduce a formalization and benchmark for the unsupervised anomaly detection task in the distribution-shift scenario.

Unsupervised Anomaly Detection

AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection

1 code implementation30 Jun 2022 Marius Dragoi, Elena Burceanu, Emanuela Haller, Andrei Manolache, Florin Brad

Analyzing the distribution shift of data is a growing research direction in nowadays Machine Learning (ML), leading to emerging new benchmarks that focus on providing a suitable scenario for studying the generalization properties of ML models.

Network Intrusion Detection Unsupervised Anomaly Detection

DATE: Detecting Anomalies in Text via Self-Supervision of Transformers

1 code implementation NAACL 2021 Andrei Manolache, Florin Brad, Elena Burceanu

Leveraging deep learning models for Anomaly Detection (AD) has seen widespread use in recent years due to superior performances over traditional methods.

Anomaly Detection

Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift

1 code implementation26 Mar 2021 Emanuela Haller, Elena Burceanu, Marius Leordeanu

The human ability to synchronize the feedback from all their senses inspired recent works in multi-task and multi-modal learning.

Multi-Task Learning Self-Supervised Learning +1

SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking

1 code implementation27 Nov 2020 Elena Burceanu

We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast 3D filtering formulation for finding the principal eigenvector of this graph's adjacency matrix.

Object Tracking

A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time

1 code implementation5 Jul 2019 Elena Burceanu, Marius Leordeanu

Our method is based on the power iteration for finding the principal eigenvector of a matrix, which we prove is equivalent to performing a specific set of 3D convolutions in the space-time feature volume.

graph partitioning Instance Segmentation +2

Learning a Robust Society of Tracking Parts using Co-occurrence Constraints

no code implementations5 Apr 2018 Elena Burceanu, Marius Leordeanu

We address this challenge by proposing a deep neural network composed of different parts, which functions as a society of tracking parts.

Object Tracking

Learning a Robust Society of Tracking Parts

no code implementations26 May 2017 Elena Burceanu, Marius Leordeanu

They are classifiers that respond at different scales and locations.

Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.